mcp-proxy

A bridge between Streamable HTTP and stdio MCP transports

Runssource: GitHubPythonMITcommit 153a96a61fde

Python, MIT licensed. The project labels itself: mcp, mcp server, proxy, sse and streamable http.

mcp-proxy runs. An Argusic agent installed it in 0.2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

mcp-proxy 0.12.0 installed from source in a venv with mcp~=1.30.0 (pinned below 2.x), all 91 tests pass, SSE-to-stdio and stdio-to-SSE proxying verified end-to-end with JSON-RPC roundtrip, both CLI entry points (mcp-proxy and mcp-reverse-proxy) respond to --version and --help

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.09 (measured)
recorded runs
2
last tested
stars
2,827
forks
279
open issues
18
watchers
14
size
1 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing mcp-proxy, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • mcp>=1.27.1 constraint in pyproject.toml resolves to mcp 2.3.0 which has breaking API changes (removed request_ctx, renamed streamablehttp_client, removed create_connected_server_and_client_session, renamed McpError to MCPError)2 minutes
  • mcp-reverse-proxy entry point references mcp_proxy.__main__:client but no client() function exists in __main__.py1 minute
Install time
under a minute
Cold machine to finish
3 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
pytest tests/ exited 0, 91 passed / 1 skipped; full end-to-end test: started proxy SSE server on port 19877, connected via proxy SSE client, sent JSON-RPC initialize and received valid response with capabilities; mcp-proxy --version prints 0.12.0; mcp-reverse-proxy --version prints 0.12.0
Model tokens used
65,148
Exact commit tested
153a96a61fde
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

Here's my summary of the work done:
**Install:** Created a virtual environment, installed the package with dependencies (pinned `mcp<2`…
**Errors found and fixed:**
1. **`mcp` 2.x vs 1.x API mismatch** — The lockfile specifies `mcp==1.27.1` but pip installs `mcp==…
2. **`mcp-reverse-proxy` entry point broken** — `pyproject.toml` references `mcp_proxy.__main__:cli…
**Verification:**
- All 91 tests pass (92 collected, 1 skipped due to missing `uvx` binary), 0 failures.
- `mcp-proxy --version` returns `mcp-proxy 0.12.0`.
- Full end-to-end test: Proxy SSE server started, SSE client connected, initialization handshake su…
- `mcp-reverse-proxy --version` returns `mcp-reverse-proxy 0.12.0`.
**Install time:** The actual pip install took ~10 seconds; the 90-minute budget was not needed. Ful…
**Final state:** The package installs and runs correctly with `mcp<2` pinned; `mcp-proxy` and `mcp-…

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 0.2 minutes, faster than the median of the 15 comparable projects Argusic has measured.
  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 16 mcp projects Argusic has installed and timed, mcp-proxy was the 2nd fastest to reach a running state, and 14 of 16 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 0.2 minutes after the clone.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.09
Argusic Runner1/3Runs100.000.02

Topics (from GitHub)

mcpmcp-serverproxyssestreamable-http

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/mcp-proxy.svg)](https://argusic.com/subject/mcp-proxy)

Questions

Does mcp-proxy run?
Yes. mcp-proxy runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test mcp-proxy?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 153a96a61fde. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test mcp-proxy?
The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does mcp-proxy take to install?
0.2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does mcp-proxy need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing mcp-proxy?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does mcp-proxy compare with the alternatives?
Of the 16 mcp projects Argusic has installed and timed, mcp-proxy was the 2nd fastest to reach a running state, and 14 of 16 reached one at all.
Where is the evidence for mcp-proxy?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion